AF prospector-lite
B2B outreach framework for OpenClaw agents. Gives your agent a structured prospecting workflow with email verification, bounce handling, pipeline tracking, duplicate prevention, domain reputation protection, and a self-improving lessons log. Built from 100+ production outreach runs. Use when the user wants their agent to do cold outreach, prospect research, lead generation, sales emails, or build a B2B pipeline. Also triggers for: 'find leads', 'send outreach', 'cold email', 'prospect list', 'sales pipeline', 'lead gen', or any request to research and contact potential customers.
As a process F 58/100 · Will not run — References files that are not bundled: YOUR_PAYMENT_LINK, YOUR_WEBSITE
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: YOUR_PAYMENT_LINK - warning
missing-refreference to a missing file: YOUR_WEBSITE
Process rating: all ten parameters 58/100
- 0Tools and files. 2 referenced file(s) missing: YOUR_PAYMENT_LINK, YOUR_WEBSITE
- 0Result and completion. Does not say what the result is
- 30Running it twice. 25 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 78 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3640 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 586: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.